MIT 6.S191 (2020): Generalizable Autonomy for Robot Manipulation

preview_player
Показать описание
MIT Introduction to Deep Learning 6.S191: Lecture 8
Generalizable Autonomy for Robot Manipulation
Lecturer: Animesh Garg (NVIDIA & University of Toronto)
January 2020

Lecture Outline
0:00 - Introduction
3:45 - Achieving generalizable autonomy
4:19 - Leveraging imitation learning
6:08 - Learning visuo-motor policies
13:09 - Learning skills
16:38 - Off-policy RL + AC-Teach
22:02 - Compositional planning
27:20 - Model-based RL
34:37 - Leveraging task structure
36:35 - Neural task programming (NTP)
43:04 - Data for robotics
44:24 - RoboTurk
45:54 - Summary

Subscribe to stay up to date with new deep learning lectures at MIT, or follow us @MITDeepLearning on Twitter and Instagram to stay fully-connected!!
  1. Alexander Amini
  2. deep learning
  3. mit
  4. artificial intelligence
  5. neural networks
  6. machine learning
Рекомендации по теме
MIT 6.S191 (2020): 0:47:00

MIT 6.S191 (2020): Generalizable Autonomy for Robot Manipulation

MIT 6.S191 (2020): 0:40:40

MIT 6.S191 (2020): Deep Generative Modeling

MIT 6.S191 (2020): 0:37:20

MIT 6.S191 (2020): Convolutional Neural Networks

MIT 6.S191: Evidential 0:48:52

MIT 6.S191: Evidential Deep Learning and Uncertainty

MIT 6.S191 (2021): 0:56:36

MIT 6.S191 (2021): Introduction to Deep Learning

MIT 6.S191 (2020): 0:41:10

MIT 6.S191 (2020): Neurosymbolic AI

MIT 6.S191 (2021): 0:55:57

MIT 6.S191 (2021): Convolutional Neural Networks

MIT 6.S191 (2021): 1:01:54

MIT 6.S191 (2021): Deep Generative Modeling

MIT 6.S191 (2021): 0:57:08

MIT 6.S191 (2021): Reinforcement Learning

MIT Deep Learning 0:01:11

MIT Deep Learning 6.S191 Teaser

MIT 6.S191 (2019): 0:36:21

MIT 6.S191 (2019): Deep Learning Limitations and New Frontiers

MIT 6.S191 (2020): 0:36:44

MIT 6.S191 (2020): Neural Rendering

Building blocks of 1:22:11

Building blocks of Generalizable Autonomy in Robotics

EI Seminar - 1:06:43

EI Seminar - Animesh Garg - Building Blocks of Generalizable Autonomy: Duality of Discovery & Bi...

MIT 6.S191 (2022): 0:53:29

MIT 6.S191 (2022): Deep Learning New Frontiers

MIT 6.S191 (2021): 0:50:46

MIT 6.S191 (2021): Deep Learning New Frontiers

MIT Introduction to 0:49:01

MIT Introduction to Deep Learning (2022) | 6.S191

MIT 6.S191: Deep 0:40:58

MIT 6.S191: Deep CPCFG for Information Extraction

MIT 6.S191: AI 0:43:22

MIT 6.S191: AI Bias and Fairness

MIT 6.S191 (2020): 0:38:52

MIT 6.S191 (2020): Machine Learning for Scent

Animesh Garg - 1:06:57

Animesh Garg - Building Blocks of Generalizable Autonomy: Duality of Discovery & Bias

MIT 6.S191 (2021): 1:00:31

MIT 6.S191 (2021): Recurrent Neural Networks

Animesh Garg 'Generalizable 1:03:37

Animesh Garg 'Generalizable Autonomy In Robotics'

Animesh Garg - 1:04:21

Animesh Garg - Building blocks of Generalizable Autonomy in Robotics

Комментарии
Автор

powerful lecture, I like kind of things like how they think and ask from themselves right questions.

darkhanzholtayev
Автор

because things change so fast this recent high level view is a great jumping off point for further study. thank you!

cagneymoreau
Автор

3:20 Any one knows the video? link plz. thanks.

hanyanglee
Автор

25:57 Machine Learning in Early Human State!!! Its learning to use the tools what ours ancestors used.!!!

Avisheknandi
Автор

Lol the subtitles at 40:09. Kinda ironic :D

minkbag
Автор

I have a question but before that first, I watched all videos till this one I grabbed like every part but couldn't understand them. Like in the first 6 lectures we got brief about the techniques of deep learning and a bunch of other stuff but these guest lectures couldn't bring anything from this, we learned beginner than directly go for the expert. Coming to the question is I would like to know what are the things needed to understand briefly, these upcoming technologies and these guest lectures? either mathematical knowledge or the knowledge about these technologies? If anyone could answer this query of mine I would be very much thankful.

RishabhJain-ukqt
Автор

It seems no one cares about robot manipulation, given that there are hundreds or even thousands of comments in other lectures.

zuyuanzhu
Автор

my dog is smarter than these robots lol.

zeesamuel